Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5051 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2612. Min Range: -1.2612

Max Act: 1.2612. Min Act: -0.0001

Data Index: 894203 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 1.2612. Min Range: -1.2612

Max Act: 1.2128. Min Act: -0.0001

Data Index: 1190149 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 1.2612. Min Range: -1.2612

Max Act: 1.1940. Min Act: -0.0001

Data Index: 1063230 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 1.2612. Min Range: -1.2612

Max Act: 1.0055. Min Act: -0.0001

Data Index: 344618 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.9503. Min Act: -0.0001

Data Index: 654843 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.9036. Min Act: -0.0001

Data Index: 1124725 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.9296. Min Act: -0.0001

Data Index: 496297 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8868. Min Act: -0.0001

Data Index: 400470 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8887. Min Act: -0.0001

Data Index: 170891 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8931. Min Act: -0.0001

Data Index: 398872 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1383595 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8744. Min Act: -0.0001

Data Index: 149304 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8320. Min Act: -0.0001

Data Index: 376892 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8267. Min Act: -0.0001

Data Index: 809252 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8347. Min Act: -0.0001

Data Index: 685184 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8116. Min Act: -0.0001

Data Index: 1053511 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.7934. Min Act: -0.0001

Data Index: 391507 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.7446. Min Act: -0.0001

Data Index: 596833 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.8377. Min Act: -0.0001

Data Index: 1180977 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.2612. Min Range: -1.2612

Max Act: 0.7633. Min Act: -0.0001

Data Index: 407193 (C4 (Web Text))

Max Activating Token Index: 381